© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45345
    Prev
    Next
    INDEX
    Explanations

    forced induction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rumbo
    -0.09
    撤
    -0.09
     anonymously
    -0.09
     dépos
    -0.09
    ப்படி
    -0.09
     deco
    -0.09
    laş
    -0.09
    旅
    -0.08
     ফিরে
    -0.08
    违
    -0.08
    POSITIVE LOGITS
     Boost
    0.11
     turbo
    0.10
    Boost
    0.10
     boost
    0.10
    boost
    0.10
     boosts
    0.09
     boosting
    0.09
     Enh
    0.09
    BOOST
    0.09
     BOOST
    0.09
    Activations Density 0.010%

    No Known Activations